Constructing a Pluralist Moral Sentence Embedding Space using Contrastive Learning

Moral values influence humans in decision-making. Pluralist moral philosophers argue that human morality can be represented by a finite number of moral values, respecting the differences in moral views. Recent advancements in NLP show that language models retain a discernible level of knowledge in deontological ethics and moral norms of society....

What would Jiminy Cricket do?: A pluralist approach in generating and processing morally-aligned text

When making decisions, people are automatically guided by their moral compass. However, AI agents need to be conditioned in order to be steered towards moral behaviour. An environment that can be used to train and test agents is the Jiminy Cricket environment. The Jiminy Cricket environment consists of a set of text-based narrative games, where...

Natural Language Processing and Reinforcement Learning to Generate Morally: What is the optimal weight w to win the games while playing morally?

In our everyday life, people interact more and more with agents. However these agents often lack a moral sense and prioritize the accomplishment of the given task. In consequence, agents may unknowingly act immorally. Little research or progress has been done to endow agents with human morality and an internal sense of right and wrong. As of...

Balancing multidimensional morality and progression: Evaluating the tradeoff for artificial agents playing text-based games

Morality is a fundamental concept that guides humans in the decision-making process. Given the rise of large language models in society, it is necessary to ensure that they adhere to human principles, among which morality is of substantial importance. While research has been done regarding artificial agents behaving morally, current state of the...

NLP and reinforcement learning to generate morally aligned text: How does explainable models perform compared to black-box models

<br/>This paper evaluates the performance of an automated explainable model, Moral- Strength, to predict morality, or more pre- cisely Moral Foundations Theory (MFT) traits. MFT is a way to represent and divide morality into precise and detailed traits. This evaluation happens in the Jiminy Cricket environment, an environ- ment composed of 25...

Natural Language Processing and Reinforcement Learning to Generate Morally Aligned Text: Comparing a moral agent to an optimally playing agent

Nowadays Large Language Models are becoming more and more prevalent in today's society. These models act without a sense of morality however. They only prioritize accomplishing their goal. Currently, little research has been done evaluating these models. The current state of the art Reinforcement Learning models represent morality by a singular...

Active Learning with Multi-annotator Disagreement

Moral values are often used as guidelines for human behaviour. The ability to identify moral values is important for social and ethical artificial intelligence. We address the difficulties of using contemporary natural language processing (NLP) techniques to classify moral values in texts. As the classification criterion of moral values is...

Moral Embeddings: A closer look at their Performance, Generalizability and Transferability

Moral values are abstract ideas that ground our judgements towards what is right or wrong. However, with the rapid unfold of moral rhetoric on social media, it becomes increasingly important to place these ideas in a moral frame, contain their harmful effects, and recognise their positive ones. So far, estimating values from opinionated text has...

Estimating the transferability of state-of-the-art models in predicting moral values

Moral values play a crucial role in our decision-making process by defining what is right and wrong. With the emergence of political activism and moral discourse on social media, and the latest developments in Natural Language Processing, we are looking at an opportunity to analyze moral values to observe trends as they form. Recent studies have...

Evaluating catastrophic forgetting of state-of-the-art NLP models for predicting moral values

Personal moral values represent the motivation behind individuals' actions and opinions. Understanding these values is helpful both in predicting individuals' actions, such as violent protests, and building AI that can better collaborate with humans. Predicting moral values is a challenging problem due to the abstract and subjective essence of...

Evaluating interpretability of state-of-the-art NLP models for predicting moral values

Understanding personal values is a crucial aspect that can facilitate the collaboration between AI and humans. Nonetheless, the implementation of collaborative agents in real life greatly depends on the amount of trust that is built in their relationship with people. In order to bridge this gap, more extensive analysis of the explainability of...

Performance analysis of the state-of-the-art NLP models for predicting moral values

Moral values are instrumental in understanding people's beliefs and behaviors. Estimating such values from text would facilitate the interaction between humans and computers. To date, no comparison between NLP models for predicting moral values from text exists. This paper addresses this by comparing LSTM and more novel models such as BERT and...